Self-Park Risk Evaluation Using Audio and Visual Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing self-park systems in vehicles do not utilize audio sensor inputs, preventing them from reacting to important auditory cues like horn honking, human speech, or animal sounds during parking maneuvers, which can indicate potential risks.
Innovation Solution
A system incorporating audio and visual sensors with a neural network to analyze sensor data, calculate a risk evaluation, and generate a confidence score to determine suitable actions, such as terminating the self-park function, implementing cautionary measures, or proceeding with the maneuver based on the score.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If audio sensors are added to the self-park system, then the vehicle's ability to detect auditory cues (horn, speech, animal sounds) is improved, but the device complexity increases
Solution Approach 1:
The system segments the sensing function into multiple specialized sensors (audio sensors, visual sensors) rather than using a single multi-functional sensor. Each sensor type is optimized for its specific modality, improving overall detection reliability while maintaining manageable complexity through functional specialization.
Solution Approach 2:
The computing device serves multiple functions: it processes data from both audio and visual sensors, performs risk evaluation, generates confidence scores, and determines appropriate actions. This multi-functionality consolidates complexity into a single processing unit rather than requiring separate systems for each function.
2Measurement precision
If audio sensor data is processed through neural network analysis, then the risk evaluation accuracy is improved, but the computing power requirement increases
Solution Approach 1:
The system applies neural network analysis selectively to audio sensor data rather than processing all sensor data through the most computationally intensive methods. This partial application of advanced processing achieves sufficient risk evaluation accuracy while managing computing power consumption by using appropriate processing intensity for each data type.
3Adaptability or versatility
If the system implements multiple action options based on confidence score, then the adaptability of the self-park system is improved, but the control complexity increases
Solution Approach 1:
The system dynamically adjusts its response based on the calculated confidence score. When confidence is high, it proceeds with the self-park maneuver; when confidence is low, it terminates the function and alerts the driver. This dynamic adaptation to varying confidence levels provides flexible response to different risk scenarios without requiring complex control logic for every possible situation.
Data Source
AI summary
Systems and methods for performing enhanced self-park maneuvers are provided. The system may comprise one or more audio sensors coupled to a vehicle configured to generate audio sensor data, one or more visual sensors coupled to the vehicle configured to generate visual sensor data, and a computing device, comprising a processor and a memory. The memory may comprise instructions that, when executed by the processor, are configured to cause the processor to cause the vehicle to perform a remote smart parking assist (RSPA) function to self-park the vehicle, receive the audio sensor data and the visual sensor data, calculate a risk evaluation based on the audio sensor data and the visual sensor data, using a neural network, generate a confidence score based on the risk evaluation, and determine one or more suitable actions for the vehicle to take, based on the confidence score.